Replacing electrons with photons is a compelling route toward high-speed,massively parallel,and low-power artificial intelligence computing.Recently,diffractive networks composed of phase surfaces were trained to perform machine learning tasks through linear optical transformations.However,the existing architectures often comprise bulky components and,most critically,they cannot mimic the human brain for multitasking.Here,we demonstrate a multi-skilled diffractive neural network based on a metasurface device,which can perform on-chip multi-channel sensing and multitasking in the visible.The polarization multiplexing scheme of the subwavelength nanostructures is applied to construct a multi-channel classifier framework for simultaneous recognition of digital and fashionable items.The areal density of the artificial neurons can reach up to 6.25×106 mm-2 multiplied by the number of channels.The metasurface is integrated with the mature complementary metal-oxide semiconductor imaging sensor,providing a chip-scale architecture to process information directly at physical layers for energy-efficient and ultra-fast image processing in machine vision,autonomous driving,and precision medicine.

Xuhao Luo;Yueqiang Hu;Xiangnian Ou;Xin Li;Jiajie Lai;Na Liu;Xinbin Cheng;Anlian Pan;Huigao Duan

National Research Center for High-Efficiency Grinding,College of Mechanical and Vehicle Engineering,Hunan University,Changsha 410082,China;Institute of Precision Optical Engineering,School of Physics Science and Engineering,Tongji University,Shanghai 200092,China;Advanced Manufacturing Laboratory of Micro-Nano Optical Devices,Shenzhen Research Institute,Hunan University,Shenzhen 518000,China;2nd Physics Institute,University of Stuttgart,Pfaffenwaldring 57,70569 Stuttgart,Germany;Max Planck Institute for Solid State Research,Heisenbergstrasse 1,70569 Stuttgart,Germany;Greater Bay Area Institute for Innovation,Hunan University,Guangzhou 511300,China

光：科学与应用（英文版）

[1]Xuhao Luo;Yueqiang Hu;Xiangnian Ou;Xin Li;Jiajie Lai;Na Liu;Xinbin Cheng;Anlian Pan;Huigao Duan-.Metasurface-enabled on-chip multiplexed diffractive neural networks in the visible)[J].光：科学与应用（英文版）,2022(07):1443-1453

multitasking,fashionable

Metasurface,enabled,chip,multiplexed,diffractive,neural,networks,visible,Replacing,electrons,photons,compelling,route,toward,high,speed,massively,parallel,low,power,artificial,intelligence,computing,Recently,composed,phase,surfaces,were,trained,perform,machine,learning,tasks,through,linear,optical,transformations,However,existing,architectures,often,comprise,bulky,components,most,critically,they,cannot,mimic,human,brain,Here,demonstrate,skilled,metasurface,device,which,sensing,polarization,multiplexing,scheme,subwavelength,nanostructures,applied,construct,classifier,framework,simultaneous,recognition,digital,items,areal,density,neurons,reach,up,multiplied,by,number,channels,integrated,mature,complementary,metal,oxide,semiconductor,imaging,sensor,providing,scale,information,directly,physical,layers,energy,efficient,ultra,fast,image,processing,vision,autonomous,driving,precision,medicine

0.690309